#include "utils/builtins.h"
#include "utils/rel.h"
+static TM_Result heapam_tuple_lock_internal(Relation relation, ItemPointer tid,
+ Snapshot snapshot, TupleTableSlot *slot,
+ CommandId cid, LockTupleMode mode,
+ LockWaitPolicy wait_policy, uint8 flags,
+ TM_FailureData *tmfd, bool updated);
+
static void reform_and_rewrite_tuple(HeapTuple tuple,
Relation OldHeap, Relation NewHeap,
Datum *values, bool *isnull, RewriteState rwstate);
static TM_Result
heapam_tuple_delete(Relation relation, ItemPointer tid, CommandId cid,
Snapshot snapshot, Snapshot crosscheck, bool wait,
- TM_FailureData *tmfd, bool changingPart)
+ TM_FailureData *tmfd, bool changingPart,
+ LazyTupleTableSlot *lockedSlot)
{
+ TM_Result result;
+
/*
* Currently Deleting of index tuples are handled at vacuum, in case if
* the storage itself is cleaning the dead tuples by itself, it is the
* time to call the index tuple deletion also.
*/
- return heap_delete(relation, tid, cid, crosscheck, wait, tmfd, changingPart);
+ result = heap_delete(relation, tid, cid, crosscheck, wait,
+ tmfd, changingPart);
+
+ /*
+ * If the tuple has been concurrently updated, then get the lock on it.
+ * (Do this if caller asked for tat by providing a 'lockedSlot'.) With the
+ * lock held retry of delete should succeed even if there are more
+ * concurrent update attempts.
+ */
+ if (result == TM_Updated && lockedSlot)
+ {
+ TupleTableSlot *evalSlot;
+
+ Assert(wait);
+
+ evalSlot = LAZY_TTS_EVAL(lockedSlot);
+ result = heapam_tuple_lock_internal(relation, tid, snapshot,
+ evalSlot, cid, LockTupleExclusive,
+ LockWaitBlock,
+ TUPLE_LOCK_FLAG_FIND_LAST_VERSION,
+ tmfd, true);
+
+ if (result == TM_Ok)
+ {
+ tmfd->traversed = true;
+ return TM_Updated;
+ }
+ }
+
+ return result;
}
heapam_tuple_update(Relation relation, ItemPointer otid, TupleTableSlot *slot,
CommandId cid, Snapshot snapshot, Snapshot crosscheck,
bool wait, TM_FailureData *tmfd,
- LockTupleMode *lockmode, TU_UpdateIndexes *update_indexes)
+ LockTupleMode *lockmode, TU_UpdateIndexes *update_indexes,
+ LazyTupleTableSlot *lockedSlot)
{
bool shouldFree = true;
HeapTuple tuple = ExecFetchSlotHeapTuple(slot, true, &shouldFree);
if (shouldFree)
pfree(tuple);
+ /*
+ * If the tuple has been concurrently updated, then get the lock on it.
+ * (Do this if caller asked for tat by providing a 'lockedSlot'.) With the
+ * lock held retry of update should succeed even if there are more
+ * concurrent update attempts.
+ */
+ if (result == TM_Updated && lockedSlot)
+ {
+ TupleTableSlot *evalSlot;
+
+ Assert(wait);
+
+ evalSlot = LAZY_TTS_EVAL(lockedSlot);
+ result = heapam_tuple_lock_internal(relation, otid, snapshot,
+ evalSlot, cid, *lockmode,
+ LockWaitBlock,
+ TUPLE_LOCK_FLAG_FIND_LAST_VERSION,
+ tmfd, true);
+
+ if (result == TM_Ok)
+ {
+ tmfd->traversed = true;
+ return TM_Updated;
+ }
+ }
+
return result;
}
TupleTableSlot *slot, CommandId cid, LockTupleMode mode,
LockWaitPolicy wait_policy, uint8 flags,
TM_FailureData *tmfd)
+{
+ return heapam_tuple_lock_internal(relation, tid, snapshot, slot, cid,
+ mode, wait_policy, flags, tmfd, false);
+}
+
+/*
+ * This routine does the work for heapam_tuple_lock(), but also support
+ * `updated` argument to re-use the work done by heapam_tuple_update() or
+ * heapam_tuple_delete() on figuring out that tuple was concurrently updated.
+ */
+static TM_Result
+heapam_tuple_lock_internal(Relation relation, ItemPointer tid,
+ Snapshot snapshot, TupleTableSlot *slot,
+ CommandId cid, LockTupleMode mode,
+ LockWaitPolicy wait_policy, uint8 flags,
+ TM_FailureData *tmfd, bool updated)
{
BufferHeapTupleTableSlot *bslot = (BufferHeapTupleTableSlot *) slot;
TM_Result result;
- Buffer buffer;
+ Buffer buffer = InvalidBuffer;
HeapTuple tuple = &bslot->base.tupdata;
bool follow_updates;
tuple_lock_retry:
tuple->t_self = *tid;
- result = heap_lock_tuple(relation, tuple, cid, mode, wait_policy,
- follow_updates, &buffer, tmfd);
+ if (!updated)
+ result = heap_lock_tuple(relation, tuple, cid, mode, wait_policy,
+ follow_updates, &buffer, tmfd);
+ else
+ result = TM_Updated;
if (result == TM_Updated &&
(flags & TUPLE_LOCK_FLAG_FIND_LAST_VERSION))
{
- /* Should not encounter speculative tuple on recheck */
- Assert(!HeapTupleHeaderIsSpeculative(tuple->t_data));
+ if (!updated)
+ {
+ /* Should not encounter speculative tuple on recheck */
+ Assert(!HeapTupleHeaderIsSpeculative(tuple->t_data));
- ReleaseBuffer(buffer);
+ ReleaseBuffer(buffer);
+ }
+ else
+ {
+ updated = false;
+ }
if (!ItemPointerEquals(&tmfd->ctid, &tuple->t_self))
{
return true;
}
+/*
+ * The implementation for LazyTupleTableSlot wrapper for EPQ slot to be passed
+ * to table_tuple_update()/table_tuple_delete().
+ */
+typedef struct
+{
+ EPQState *epqstate;
+ ResultRelInfo *resultRelInfo;
+} GetEPQSlotArg;
+
+static TupleTableSlot *
+GetEPQSlot(void *arg)
+{
+ GetEPQSlotArg *slotArg = (GetEPQSlotArg *) arg;
+
+ return EvalPlanQualSlot(slotArg->epqstate,
+ slotArg->resultRelInfo->ri_RelationDesc,
+ slotArg->resultRelInfo->ri_RangeTableIndex);
+}
+
/*
* ExecDeleteAct -- subroutine for ExecDelete
*
* Actually delete the tuple from a plain table.
*
+ * If the 'lockUpdated' flag is set and the target tuple is updated, then
+ * the latest version gets locked and fetched into the EPQ slot.
+ *
* Caller is in charge of doing EvalPlanQual as necessary
*/
static TM_Result
ExecDeleteAct(ModifyTableContext *context, ResultRelInfo *resultRelInfo,
- ItemPointer tupleid, bool changingPart)
+ ItemPointer tupleid, bool changingPart, bool lockUpdated)
{
EState *estate = context->estate;
+ GetEPQSlotArg slotArg = {context->epqstate, resultRelInfo};
+ LazyTupleTableSlot lazyEPQSlot,
+ *lazyEPQSlotPtr;
+ if (lockUpdated)
+ {
+ MAKE_LAZY_TTS(&lazyEPQSlot, GetEPQSlot, &slotArg);
+ lazyEPQSlotPtr = &lazyEPQSlot;
+ }
+ else
+ {
+ lazyEPQSlotPtr = NULL;
+ }
return table_tuple_delete(resultRelInfo->ri_RelationDesc, tupleid,
estate->es_output_cid,
estate->es_snapshot,
estate->es_crosscheck_snapshot,
true /* wait for commit */ ,
&context->tmfd,
- changingPart);
+ changingPart,
+ lazyEPQSlotPtr);
}
/*
* transaction-snapshot mode transactions.
*/
ldelete:
- result = ExecDeleteAct(context, resultRelInfo, tupleid, changingPart);
+ result = ExecDeleteAct(context, resultRelInfo, tupleid, changingPart,
+ !IsolationUsesXactSnapshot());
switch (result)
{
errmsg("could not serialize access due to concurrent update")));
/*
- * Already know that we're going to need to do EPQ, so
- * fetch tuple directly into the right slot.
+ * ExecDeleteAct() has already locked the old tuple for
+ * us. Now we need to copy it to the right slot.
*/
EvalPlanQualBegin(context->epqstate);
inputslot = EvalPlanQualSlot(context->epqstate, resultRelationDesc,
resultRelInfo->ri_RangeTableIndex);
- result = table_tuple_lock(resultRelationDesc, tupleid,
- estate->es_snapshot,
- inputslot, estate->es_output_cid,
- LockTupleExclusive, LockWaitBlock,
- TUPLE_LOCK_FLAG_FIND_LAST_VERSION,
- &context->tmfd);
-
- switch (result)
+ /*
+ * Save locked table for further processing for RETURNING
+ * clause.
+ */
+ if (processReturning &&
+ resultRelInfo->ri_projectReturning &&
+ !resultRelInfo->ri_FdwRoutine)
{
- case TM_Ok:
- Assert(context->tmfd.traversed);
+ TupleTableSlot *returningSlot;
- /*
- * Save locked tuple for further processing of
- * RETURNING clause.
- */
- if (processReturning &&
- resultRelInfo->ri_projectReturning &&
- !resultRelInfo->ri_FdwRoutine)
- {
- TupleTableSlot *returningSlot;
-
- returningSlot = ExecGetReturningSlot(estate, resultRelInfo);
- ExecCopySlot(returningSlot, inputslot);
- ExecMaterializeSlot(returningSlot);
- }
-
- epqslot = EvalPlanQual(context->epqstate,
- resultRelationDesc,
- resultRelInfo->ri_RangeTableIndex,
- inputslot);
- if (TupIsNull(epqslot))
- /* Tuple not passing quals anymore, exiting... */
- return NULL;
-
- /*
- * If requested, skip delete and pass back the
- * updated row.
- */
- if (epqreturnslot)
- {
- *epqreturnslot = epqslot;
- return NULL;
- }
- else
- goto ldelete;
-
- case TM_SelfModified:
-
- /*
- * This can be reached when following an update
- * chain from a tuple updated by another session,
- * reaching a tuple that was already updated in
- * this transaction. If previously updated by this
- * command, ignore the delete, otherwise error
- * out.
- *
- * See also TM_SelfModified response to
- * table_tuple_delete() above.
- */
- if (context->tmfd.cmax != estate->es_output_cid)
- ereport(ERROR,
- (errcode(ERRCODE_TRIGGERED_DATA_CHANGE_VIOLATION),
- errmsg("tuple to be deleted was already modified by an operation triggered by the current command"),
- errhint("Consider using an AFTER trigger instead of a BEFORE trigger to propagate changes to other rows.")));
- return NULL;
-
- case TM_Deleted:
- /* tuple already deleted; nothing to do */
- return NULL;
+ returningSlot = ExecGetReturningSlot(estate,
+ resultRelInfo);
+ ExecCopySlot(returningSlot, inputslot);
+ ExecMaterializeSlot(returningSlot);
+ }
- default:
+ Assert(context->tmfd.traversed);
+ epqslot = EvalPlanQual(context->epqstate,
+ resultRelationDesc,
+ resultRelInfo->ri_RangeTableIndex,
+ inputslot);
+ if (TupIsNull(epqslot))
+ /* Tuple not passing quals anymore, exiting... */
+ return NULL;
- /*
- * TM_Invisible should be impossible because we're
- * waiting for updated row versions, and would
- * already have errored out if the first version
- * is invisible.
- *
- * TM_Updated should be impossible, because we're
- * locking the latest version via
- * TUPLE_LOCK_FLAG_FIND_LAST_VERSION.
- */
- elog(ERROR, "unexpected table_tuple_lock status: %u",
- result);
- return NULL;
+ /*
+ * If requested, skip delete and pass back the updated
+ * row.
+ */
+ if (epqreturnslot)
+ {
+ *epqreturnslot = epqslot;
+ return NULL;
}
-
- Assert(false);
- break;
+ else
+ goto ldelete;
}
case TM_Deleted:
static TM_Result
ExecUpdateAct(ModifyTableContext *context, ResultRelInfo *resultRelInfo,
ItemPointer tupleid, HeapTuple oldtuple, TupleTableSlot *slot,
- bool canSetTag, UpdateContext *updateCxt)
+ bool canSetTag, bool lockUpdated, UpdateContext *updateCxt)
{
EState *estate = context->estate;
Relation resultRelationDesc = resultRelInfo->ri_RelationDesc;
bool partition_constraint_failed;
TM_Result result;
+ GetEPQSlotArg slotArg = {context->epqstate, resultRelInfo};
+ LazyTupleTableSlot lazyEPQSlot,
+ *lazyEPQSlotPtr;
updateCxt->crossPartUpdate = false;
* for referential integrity updates in transaction-snapshot mode
* transactions.
*/
+ if (lockUpdated)
+ {
+ MAKE_LAZY_TTS(&lazyEPQSlot, GetEPQSlot, &slotArg);
+ lazyEPQSlotPtr = &lazyEPQSlot;
+ }
+ else
+ {
+ lazyEPQSlotPtr = NULL;
+ }
result = table_tuple_update(resultRelationDesc, tupleid, slot,
estate->es_output_cid,
estate->es_snapshot,
estate->es_crosscheck_snapshot,
true /* wait for commit */ ,
&context->tmfd, &updateCxt->lockmode,
- &updateCxt->updateIndexes);
+ &updateCxt->updateIndexes,
+ lazyEPQSlotPtr);
if (result == TM_Ok)
updateCxt->updated = true;
static TupleTableSlot *
ExecUpdate(ModifyTableContext *context, ResultRelInfo *resultRelInfo,
ItemPointer tupleid, HeapTuple oldtuple, TupleTableSlot *slot,
- bool canSetTag)
+ bool canSetTag, bool locked)
{
EState *estate = context->estate;
Relation resultRelationDesc = resultRelInfo->ri_RelationDesc;
*/
redo_act:
result = ExecUpdateAct(context, resultRelInfo, tupleid, oldtuple, slot,
- canSetTag, &updateCxt);
+ canSetTag, !IsolationUsesXactSnapshot(),
+ &updateCxt);
/*
* If ExecUpdateAct reports that a cross-partition update was done,
ereport(ERROR,
(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
errmsg("could not serialize access due to concurrent update")));
+ Assert(!locked);
/*
- * Already know that we're going to need to do EPQ, so
- * fetch tuple directly into the right slot.
+ * ExecUpdateAct() has already locked the old tuple for
+ * us. Now we need to copy it to the right slot.
*/
inputslot = EvalPlanQualSlot(context->epqstate, resultRelationDesc,
resultRelInfo->ri_RangeTableIndex);
- result = table_tuple_lock(resultRelationDesc, tupleid,
- estate->es_snapshot,
- inputslot, estate->es_output_cid,
- updateCxt.lockmode, LockWaitBlock,
- TUPLE_LOCK_FLAG_FIND_LAST_VERSION,
- &context->tmfd);
-
- switch (result)
- {
- case TM_Ok:
- Assert(context->tmfd.traversed);
-
- /* Make sure ri_oldTupleSlot is initialized. */
- if (unlikely(!resultRelInfo->ri_projectNewInfoValid))
- ExecInitUpdateProjection(context->mtstate,
- resultRelInfo);
-
- /*
- * Save the locked tuple for further calculation
- * of the new tuple.
- */
- oldSlot = resultRelInfo->ri_oldTupleSlot;
- ExecCopySlot(oldSlot, inputslot);
- ExecMaterializeSlot(oldSlot);
-
- epqslot = EvalPlanQual(context->epqstate,
- resultRelationDesc,
- resultRelInfo->ri_RangeTableIndex,
- inputslot);
- if (TupIsNull(epqslot))
- /* Tuple not passing quals anymore, exiting... */
- return NULL;
-
- slot = ExecGetUpdateNewTuple(resultRelInfo,
- epqslot, oldSlot);
- goto redo_act;
-
- case TM_Deleted:
- /* tuple already deleted; nothing to do */
- return NULL;
-
- case TM_SelfModified:
-
- /*
- * This can be reached when following an update
- * chain from a tuple updated by another session,
- * reaching a tuple that was already updated in
- * this transaction. If previously modified by
- * this command, ignore the redundant update,
- * otherwise error out.
- *
- * See also TM_SelfModified response to
- * table_tuple_update() above.
- */
- if (context->tmfd.cmax != estate->es_output_cid)
- ereport(ERROR,
- (errcode(ERRCODE_TRIGGERED_DATA_CHANGE_VIOLATION),
- errmsg("tuple to be updated was already modified by an operation triggered by the current command"),
- errhint("Consider using an AFTER trigger instead of a BEFORE trigger to propagate changes to other rows.")));
- return NULL;
+ /* Make sure ri_oldTupleSlot is initialized. */
+ if (unlikely(!resultRelInfo->ri_projectNewInfoValid))
+ ExecInitUpdateProjection(context->mtstate,
+ resultRelInfo);
- default:
- /* see table_tuple_lock call in ExecDelete() */
- elog(ERROR, "unexpected table_tuple_lock status: %u",
- result);
- return NULL;
- }
+ /*
+ * Save the locked tuple for further calculation of the
+ * new tuple.
+ */
+ oldSlot = resultRelInfo->ri_oldTupleSlot;
+ ExecCopySlot(oldSlot, inputslot);
+ ExecMaterializeSlot(oldSlot);
+ Assert(context->tmfd.traversed);
+
+ epqslot = EvalPlanQual(context->epqstate,
+ resultRelationDesc,
+ resultRelInfo->ri_RangeTableIndex,
+ inputslot);
+ if (TupIsNull(epqslot))
+ /* Tuple not passing quals anymore, exiting... */
+ return NULL;
+ slot = ExecGetUpdateNewTuple(resultRelInfo,
+ epqslot, oldSlot);
+ goto redo_act;
}
break;
*returning = ExecUpdate(context, resultRelInfo,
conflictTid, NULL,
resultRelInfo->ri_onConflict->oc_ProjSlot,
- canSetTag);
+ canSetTag, true);
/*
* Clear out existing tuple, as there might not be another conflict among
break; /* concurrent update/delete */
}
result = ExecUpdateAct(context, resultRelInfo, tupleid, NULL,
- newslot, false, &updateCxt);
+ newslot, false, false, &updateCxt);
if (result == TM_Ok && updateCxt.updated)
{
ExecUpdateEpilogue(context, &updateCxt, resultRelInfo,
return true; /* "do nothing" */
break; /* concurrent update/delete */
}
- result = ExecDeleteAct(context, resultRelInfo, tupleid, false);
+ result = ExecDeleteAct(context, resultRelInfo, tupleid,
+ false, false);
if (result == TM_Ok)
{
ExecDeleteEpilogue(context, resultRelInfo, tupleid, NULL,
/* Now apply the update. */
slot = ExecUpdate(&context, resultRelInfo, tupleid, oldtuple,
- slot, node->canSetTag);
+ slot, node->canSetTag, false);
break;
case CMD_DELETE:
Snapshot crosscheck,
bool wait,
TM_FailureData *tmfd,
- bool changingPart);
+ bool changingPart,
+ LazyTupleTableSlot *lockedSlot);
/* see table_tuple_update() for reference about parameters */
TM_Result (*tuple_update) (Relation rel,
bool wait,
TM_FailureData *tmfd,
LockTupleMode *lockmode,
- TU_UpdateIndexes *update_indexes);
+ TU_UpdateIndexes *update_indexes,
+ LazyTupleTableSlot *lockedSlot);
/* see table_tuple_lock() for reference about parameters */
TM_Result (*tuple_lock) (Relation rel,
}
/*
- * Delete a tuple.
+ * Delete a tuple (or lock last tuple version if lockedSlot is given).
*
* NB: do not call this directly unless prepared to deal with
* concurrent-update conditions. Use simple_table_tuple_delete instead.
* tmfd - filled in failure cases (see below)
* changingPart - true iff the tuple is being moved to another partition
* table due to an update of the partition key. Otherwise, false.
+ * lockedSlot - lazy slot to save the locked tuple if should lock the last
+ * row version during the concurrent update. NULL if not needed.
*
* Normal, successful return value is TM_Ok, which means we did actually
* delete it. Failure return codes are TM_SelfModified, TM_Updated, and
static inline TM_Result
table_tuple_delete(Relation rel, ItemPointer tid, CommandId cid,
Snapshot snapshot, Snapshot crosscheck, bool wait,
- TM_FailureData *tmfd, bool changingPart)
+ TM_FailureData *tmfd, bool changingPart,
+ LazyTupleTableSlot *lockedSlot)
{
return rel->rd_tableam->tuple_delete(rel, tid, cid,
snapshot, crosscheck,
- wait, tmfd, changingPart);
+ wait, tmfd, changingPart,
+ lockedSlot);
}
/*
- * Update a tuple.
+ * Update a tuple (or lock last tuple version if lockedSlot is given).
*
* NB: do not call this directly unless you are prepared to deal with
* concurrent-update conditions. Use simple_table_tuple_update instead.
* lockmode - filled with lock mode acquired on tuple
* update_indexes - in success cases this is set to true if new index entries
* are required for this tuple
- *
+ * lockedSlot - lazy slot to save the locked tuple if should lock the last
+ * row version during the concurrent update. NULL if not needed.
+
* Normal, successful return value is TM_Ok, which means we did actually
* update it. Failure return codes are TM_SelfModified, TM_Updated, and
* TM_BeingModified (the last only possible if wait == false).
table_tuple_update(Relation rel, ItemPointer otid, TupleTableSlot *slot,
CommandId cid, Snapshot snapshot, Snapshot crosscheck,
bool wait, TM_FailureData *tmfd, LockTupleMode *lockmode,
- TU_UpdateIndexes *update_indexes)
+ TU_UpdateIndexes *update_indexes,
+ LazyTupleTableSlot *lockedSlot)
{
return rel->rd_tableam->tuple_update(rel, otid, slot,
cid, snapshot, crosscheck,
wait, tmfd,
- lockmode, update_indexes);
+ lockmode, update_indexes,
+ lockedSlot);
}
/*
projects / users / rhaas / postgres.git / commitdiff